{"id":"W4313309314","doi":"10.1101/2022.12.14.22283419","title":"Using Social Media to Help Understand Long COVID Patient Reported Health Outcomes: A Natural Language Processing Approach","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Respiratory and Cough-Related Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Telus (Canada); Queen's University; Roche (Canada); Vector Institute; University Health Network; University of Toronto","funders":"","keywords":"Social media; Anxiety; Headaches; Medicine; Coronavirus disease 2019 (COVID-19); Distress; Psychology; Disease; Psychiatry; Clinical psychology; Infectious disease (medical specialty); Computer science; Pathology; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003253395,0.001085618,0.000399204,0.006830926,0.0004776514,0.001941538,0.0005996741,0.0008442007,0.002989059],"category_scores_gemma":[0.01378706,0.0002186643,0.001040235,0.002899671,0.0005642193,0.002174362,0.001644182,0.001129261,0.001548945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004591,"about_ca_system_score_gemma":0.0009041684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005595011,"about_ca_topic_score_gemma":0.008862864,"domain_scores_codex":[0.9979599,0.00090907,0.0002871221,0.0004650059,0.0002794281,0.00009956933],"domain_scores_gemma":[0.9853924,0.01162338,0.001379915,0.0005326924,0.0009213043,0.0001503371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001440007,0.001061281,0.1764725,0.006965599,0.000851695,0.00474242,0.01197823,0.01880481,0.03029068,0.01554435,0.05367239,0.678176],"study_design_scores_gemma":[0.0002136355,0.000728506,0.2445936,0.001879344,0.0007974198,0.002689539,0.01842307,0.5126143,0.01706975,0.08213656,0.1184949,0.0003594506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3809905,0.004267212,0.4308325,0.01162745,0.001005606,0.0026642,0.1440614,0.007242695,0.01730847],"genre_scores_gemma":[0.7200869,0.00127609,0.2191933,0.001026269,0.0006189368,0.001600975,0.05366128,0.0002054277,0.00233082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006830926,"threshold_uncertainty_score":0.01720583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1661532929294269,"score_gpt":0.4129938952276986,"score_spread":0.2468406022982717,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}